A STATISTICAL MODEL OF CHANGES IN ASSET PRICES EMPLOYING INTRADAY DATA: A RECURSIVE APPROACH

This paper develops a statistical model of changes in asset prices employing intraday data. The procedure proposed in this paper is an alternative to the Hausman, Lo, and MacKinlay (1992) ordered probit model. Similar to the ordered probit model, our model also contains the linear regression model as a special case. However, compared to the ordered probit model, our specification is parsimonious. Parsimony does come at a cost, but for certain applications where, for example, a benchmark return is needed in intraday studies, there is value in terms of the computational effort required and the method's robustness to various empirical microstructure phenomena. The parsimony is achieved when statistical implications arising from intraday structural changes, which may due to such factors as concentrated trading patterns, are incorporated into a statistical model.     

经济政策不确定性、声誉机制与信用评级

本文以2007-2019年我国企业债券为样本,采用有序Probit回归模型探讨经济政策不确定性对信用评级的影响,研究结果表明：(1)经济政策不确定性的增加会促使评级机构显著降低信用评级,这种影响因产权性质存在显著差异,而且在债券市场刚性兑付被打破后更为显著;(2)声誉机制对上述影响产生积极的调节效应,声誉受损或声誉水平较高的评级机构会更加谨慎地评估经济政策不确定性的影响效应。基于此,政府应合理管控政策的出台和调整以增强社会预期,监管机构要不断强化对评级机构的监管,促使评级机构提高信用评级的质量。     

Modeling Eurobond credit ratings and forecasting downgrade probability

This article proposes and empirically tests a two-step model to forecast the downgrade probability of sterling-denominated Eurobonds. In the first step, the conditional expectation of credit rating is estimated, employing an ordered probit. In the second step, the likelihood of downgrade is modeled using credit rating, as obtained from the conditional mean in the first step, alongside with traditional operating measures in a binary-probit framework. By parameterizing a system of two equations, we are able to accommodate the disentangled effect of credit quality and company financial information on the downgrade risk. We find evidence of a nonlinear response to shifts in both credit rating and leverage. The model's forecasting performance is ascertained by means of cross validation and is benchmarked against both a naive model and a neural network model.     

A re-examination of the impact of credit ratings and economic factors on state bond yields

In this article we re-examine the impact of credit ratings and economic factors on state bond yields using a two-step model. In the first step, we adopt an ordered probit technique to obtain consistent estimates of state bond default risk. In the second step, we estimate state bond risk premiums using a regression analysis with a categorized risk variable obtained from the first step. Similar to Terza (1987) and Hsiao (1983), the model involves a categorized ordinal explanatory (rating) variable. However, our two-step model deals with a case where category thresholds are unknown and dependent on economic factors. The model provides consistent estimates for the effects of ratings and economic factors on state bond yields. Contrary to previous findings, we find that state bond yields are mainly affected by fundamental economic variables.     

Bank-firm relationship and credit risk: An analysis on Tunisian firms

This paper analyses the impact of the intensity and length of bank-firm lending relationship on Tunisian banks’ credit risk over the period 2001–2012. The sample includes 494 bank-firm relationships for 383 firms. By applying probit and ordered probit models, our results indicate that firms which engage in intense relationships with banks are less likely to encounter a credit default. In addition, these firms exhibit a higher loan quality. However, no evidence has been found for the impact of the relationship length on credit risk. Further, the findings show that private banks, unlike public financial institutions, take advantage of their close lending relationships with borrowers to mitigate information asymmetry and therefore improve their loans portfolio quality.     

The ordered qualitative model for credit rating transitions

Information on the expected changes in credit quality of obligors is contained in credit migration matrices which trace out the movements of firms across ratings categories in a given period of time and in a given group of bond issuers. The rating matrices provided by Moody's, Standard & Poor's and Fitch became crucial inputs to many applications, including the assessment of risk on corporate credit portfolios (CreditVar) and credit derivatives pricing. We propose a factor probit model for modeling and prediction of credit rating matrices that are assumed to be stochastic and driven by a latent factor. The filtered latent factor path reveals the effect of the economic cycle on corporate credit ratings, and provides evidence in support of the PIT (point-in-time) rating philosophy. The factor probit model also yields the estimates of cross-sectional correlations in rating transitions that are documented empirically but not fully accounted for in the literature and in the regulatory rules established by the Basle Committee.     

The Determinants of Credit Ratings in the United Kingdom Insurance Industry

This paper examines the determinants of external credit ratings attained by insurance firms in the United Kingdom (UK) and of the likelihood that insurers will have such an assessment. Using panel data relating to A.M. Best‐rated and Standard and Poor's (S&P)‐rated insurers over the period 1993–1997, a trichotomous logit model and an ordered probit model with sample selection are employed to show that the factors which influence the likelihood of having external credit assessments not only vary between the two agencies but also differ from those which determine the ratings themselves. Our results are shown to be of potential interest to participants in the insurance industry and policy‐makers alike.     

A random effects ordered probit model for rating migrations

Employing a random effects ordered probit model, this paper examines the sources of heterogeneity in sovereign credit ratings in emerging economies. The analysis uses data from six rating agencies for 90 countries. The model highlights the importance of considering the cross-section error, which captures country-specific heterogeneity, in modelling rating upgrades. Watchlist status is a powerful tool in predicting future rating upgrades/downgrades, and dominates rating momentum in some cases. Rating duration and existing rating are important determinants of rating migrations. Evidence of inter-agency differences and dissimilar behaviour of upgrades and downgrades is presented.     

Credit rating model development: An ordered analysis based on accounting data

In this paper we propose and test a methodology for constructing a credit rating model. We follow a polytomous ordered probit analysis leading to the specification of statistically significant credit rating intervals. We test our model with accounting data of Greek listed firms over the years 2004–2013, a period which includes both the pre-crisis growth and the crisis phase of the Greek economy and the stock market. Using the empirically—based rating categories that the model generates endogenously, we observe not only a clear and timely response of ratings to the changing economic environment, but we also obtain significant predictive ability over a period of one, two and three years.     

Determinants of Credit Constraints: Evidence from Sindh,Pakistan

This article investigates the determinants of credit constraints: evidence from Sindh, Pakistan. Cross-sectional farm-level data is collected during November and December 2016. A sample of 180 farm households is selected for interviews by using a multistage, random sampling technique. This study employed a probit regression model, frequency counts, and percentages to analyze the data. Access to formal agricultural credit is relatively low in Sindh province of Pakistan, the findings of the study show that the major constraints comprise distance to the formal credit sources, lending procedure, time lag, and interest rate whereas land ownership has a negative association and reduces the constraints to access formal credit. The findings of this study also show that for efficient allocation of resources, institutional sources of credit preferred to disburse agricultural credits toward educated and young age farmers as they are more inclined to adopt new farm technology for better farm production.     

Sovereign credit rating determinants: A comparison before and after the European debt crisis

This paper compares the importance of different sovereign credit rating determinants over time, using a sample of 90 countries for the years 2002–2015. Applying the composite marginal likelihood approach, we estimate a multi-year ordered probit model for each of the three major credit rating agencies. After the start of the European debt crisis in 2009, the importance of the financial balance, the economic development and the external debt increased substantially and the effect of eurozone membership switched from positive to negative. In addition, GDP growth gained a lot of importance for highly indebted sovereigns and government debt became much more important for countries with a low GDP growth rate. These findings provide empirical evidence that the credit rating agencies changed their sovereign credit rating assessment after the start of the European debt crisis.     

A hybrid bankruptcy prediction model with dynamic loadings on accounting-ratio-based and market-based information: A binary quantile regression approach

While using the binary quantile regression (BQR) model, we establish a hybrid bankruptcy prediction model with dynamic loadings for both the accounting-ratio-based and market-based information. Using the proposed model, we conduct an empirical study on a dataset comprising of default events during the period from 1996 to 2006. In this study, those firms experienced bankruptcy/liquidation events as defined by the Compustat database are classified as “defaulted” firms, whereas all other firms listed in the Fortune 500 with over a B-rating during the same time period are identified as “survived” firms. The empirical findings of this study are consistent with the following notions. The distance-to-default (DD) variable derived from the market-based model is statistically significant in explaining the observed default events, particularly of those firms with relatively poor credit quality (i.e., high credit risk). Conversely, the z-score obtained with the accounting-ratio-based approach is statistically significant in predicting bankruptcies of firms of relatively good credit quality (i.e., low credit risk). In-sample and out-of-sample bankruptcy prediction tests demonstrated the superior performance of utilizing dynamic loadings rather than constant loadings derived by the conventional logit model.     

Predicting bankruptcy using the discrete-time semiparametric hazard model

The usual bankruptcy prediction models are based on single-period data from firms. These models ignore the fact that the characteristics of firms change through time, and thus they may suffer from a loss of predictive power. In recent years, a discrete-time parametric hazard model has been proposed for bankruptcy prediction using panel data from firms. This model has been demonstrated by many examples to be more powerful than the traditional models. In this paper, we propose an extension of this approach allowing for a more flexible choice of hazard function. The new method does not require the assumption of a parametric model for the hazard function. In addition, it also provides a tool for checking the adequacy of the parametric model, if necessary. We use real panel datasets to illustrate the proposed method. The empirical results confirm that the new model compares favorably with the well-known discrete-time parametric hazard model.     

Liquidity and market makers: a pseudo-experimental analysis with ultrahigh frequency data

An analysis is given of the effect of market makers on liquidity using a transaction-level database. For this purpose, the focus is on a financial market where a change in regulations created explicitly the category of market maker in 1997 and that date is used to construct a pseudo-experiment. In contrast with other studies that use ultrahigh frequency data, the days to be analysed are selected using a statistical procedure to match observations before and after the change in regulation. The propensity score is used to perform the matching. After choosing the days, an estimate of an ordered probit model is made to explain the intraday behaviour of price changes. The coefficient estimates from the ordered probit model are used to calculate a measure of liquidity based on the steepness of the response function of price changes to volume. The results show that liquidity, measured in this way, has not been affected by the introduction of the market makers.     

Credit rating dynamics in the presence of unknown structural breaks

In many credit risk and pricing applications, credit transition matrix is modeled by a constant transition probability or generator matrix for Markov processes. Based on empirical evidence, we model rating transition processes as piecewise homogeneous Markov chains with unobserved structural breaks. The proposed model provides explicit formulas for the posterior distribution of the time-varying rating transition generator matrices, the probability of structural break at each period and prediction of transition matrices in the presence of possible structural breaks. Estimating the model by credit rating history, we show that the structural break in rating transitions can be captured by the proposed model. We also show that structural breaks in rating dynamics are different for different industries. We then compare the prediction performance of the proposed and time-homogeneous Markov chain models.     

The Declining Credit Quality of U.S. Corporate Debt: Myth or Reality?

In recent years, the number of downgrades in corporate bond ratings has exceeded the number of upgrades, leading some to conclude that the credit quality of U.S. corporate debt has declined. However, an alternative explanation of this apparent decline in credit quality is that the rating agencies are now using more stringent standards in assigning ratings. An ordered probit analysis of a panel of firms from 1978 through 1995 suggests that rating standards have indeed become more stringent, implying that at least part of the downward trend in ratings is the result of changing standards.     

Stochastic Migration Models with Application to Corporate Risk

In this article we explain how to use rating histories providedby the internal scoring systems of banks and rating agenciesin order to predict the future risk of a set of borrowers. Themethod is developed following the steps suggested by the BasleCommittee. To introduce both migration correlation and non-Markovianserial dependence, we consider rating histories with stochastictransition matrices. We develop the methodology to estimateboth the number and dynamics of the factors influencing thetransitions and we explain how to use the model for prediction.As an illustration, the ordered probit model with unobservabledynamic factor is estimated from French data on corporate risk.     

Newswire messages and sovereign credit ratings: Evidence from European countries under austerity reform programmes

The paper examines the role of newswire messages during the European debt crisis. In particular, this study quantifies how this news metric, revealed by statements electronically recorded, as well as by newspaper articles, affects credit ratings. Through a sample of three European countries with sovereign debt problems and under strict austerity programmes, i.e., Greece, Ireland, and Portugal, daily data spanning the period of 2009 to 2011, and parametric, nonparametric and ordered probit panel methodologies, the obtained results document that the news variable significantly affects credit ratings, particularly when news comes from market sources but less so when the news is from politicians.     

A Multicriteria Approach for Modeling Small Enterprise Credit Rating: Evidence from China

ABSTRACT

As the engine of China’s economy, small enterprises have been the central to the country’s economic development. However, given the characteristics of the small enterprises loan (i.e., short borrowing period, large volume, small amount and incomplete information), it is extremely challenging for financial institutions to assess their creditworthiness. Thus, it seriously delays and restricts the financing access for small enterprises. In an attempt to relieve the financing difficulty of small enterprises, this article makes use of 687 small wholesale and retail enterprises in a regional commercial bank in China, to establish a credit rating indicator system composed of 17 indicators by using both partial correlation analysis and probit regression. It then utilizes TOPSIS together with fuzzy C-means to score the credit ratings of our sample of small enterprises. With the dual test of default discrimination and ROC curve, the prediction accuracy of the established indicator system has reached 80.10% and 0.917, respectively, indicating the robustness and validity of our credit rating system.     

Increased presence of foreign investors and dividend policy of Japanese firms

This paper investigates the impact of the increased presence of foreign investors on the dividend policy of Japanese firms. A choice-to-pay model, estimated with a random-effects binary probit method, shows that a higher level of foreign ownership is associated with a significantly higher probability of dividend payouts. A choice-to-change model, estimated with a random-effects generalized ordered probit method, shows that a higher level of foreign ownership is associated with a significantly higher (lower) probability of an increase (no change) in dividends, while a larger 1-year increase is associated with a significantly higher (lower) probability of an increase (decrease).